Computer program, image output method, and image output device

Abstract

The invention provides a computer program, an image output method, and an image output apparatus. The computer executes the following processes: acquiring information of a peritoneal dialysis patient including at least one of edema, urine volume and water removal volume; generating an image representing a bodily fluid condition of the peritoneal dialysis patient based on the acquired information; and outputting the generated image.

Description

Technical Field

[0001] This disclosure relates to computer programs, image output methods, and image output devices. Background Technology

[0002] Previously, various techniques have been proposed for monitoring the condition of patients during dialysis treatment. For example, patent documents disclose techniques for dividing dialysis treatment into multiple sessions and measuring the patient's blood pressure during each session.

[0003] Existing technical documents

[0004] Patent documents

[0005] Patent Document 1: Japanese Patent Application Publication No. 2000-000217 Summary of the Invention

[0006] The problem that the invention aims to solve

[0007] In Patent Document 1, the focus is merely on managing blood pressure fluctuations during dialysis, and peritoneal dialysis patients and medical professionals cannot directly monitor the patient's own fluid status.

[0008] One objective is to provide computer programs, image output methods, and image output devices that can intuitively monitor the fluid status of peritoneal dialysis patients.

[0009] Methods for solving problems

[0010] (1) The computer program disclosed herein is a computer program for causing a computer to perform the following processes: acquiring information of a peritoneal dialysis patient including at least one of edema, urine output and water removal; generating an image representing the fluid status of the peritoneal dialysis patient based on the acquired information; and outputting the generated image.

[0011] (2) In the computer program of (1) above, preferably, the information also includes information related to at least one of hANP (human atrial natriuretic peptide), cardiothoracic ratio, bioimpedance, transperitoneal sodium removal and urinary sodium excretion.

[0012] (3) In the computer program of (1) or (2) above, preferably, the information also includes information related to at least one of the peritoneal dialysis patient’s weight, thirst, antihypertensive agent, diuretic and blood pressure.

[0013] (4) In any of the computer programs described in (1) to (3) above, it is preferred that the information further includes information relating to at least one of urinary cortisol, urinary creatinine, skin sodium levels and Na-MRI (nuclear magnetic resonance imaging).

[0014] (5) In any of the computer programs described in (1) to (4) above, it is preferred to generate an image that schematically represents the sodium reserves and sodium excretion of the peritoneal dialysis patient as the image.

[0015] (6) In any of the computer programs described in (1) to (5) above, it is preferable to generate an image as the image containing a first container for containing interstitial fluid and a second container for containing plasma, and to represent the amount of sodium storage based on the amount of interstitial fluid in the first container.

[0016] (7) In any of the computer programs described in (1) to (6) above, preferably, as the image, an image is generated containing a flow path through which the interstitial fluid and the plasma flow between the first container and the second container and an excretion path through which sodium is excreted from the second container in the form of urine, the image schematically representing the amount of sodium excreted based on the amount of sodium removed from the plasma by peritoneal dialysis and the amount of sodium excreted through the excretion path.

[0017] (8) In any of the computer programs described in (1) to (7) above, it is preferred to generate an image that schematically represents the balance between sodium intake and sodium excretion of the peritoneal dialysis patient as the image.

[0018] (9) In any of the computer programs described in (1) to (8) above, preferably, the acquired information of the peritoneal dialysis patient is input into a learning model, and a calculation based on the learning model is performed, wherein the learning model learns to output information related to body fluid status when information related to at least one of edema, urine output and water removal is input, and the computer program generates an image representing the body fluid status of the peritoneal dialysis patient based on the calculation result of the learning model.

[0019] (10) The image output method of this disclosure is performed by a computer as follows: acquiring information of a peritoneal dialysis patient including at least one of edema, urine output and water removal; generating an image representing the fluid status of the peritoneal dialysis patient based on the acquired information; and outputting the generated image.

[0020] (11) The image output device of the present disclosure includes at least one processor, which acquires information of a peritoneal dialysis patient including at least one of edema, urine output and water removal; generates an image representing the fluid status of the peritoneal dialysis patient based on the acquired information; and outputs the generated image.

[0021] Invention Effects

[0022] In one aspect, it allows for a direct understanding of the fluid status of peritoneal dialysis patients. Attached Figure Description

[0023] Figure 1 This is a schematic diagram illustrating an example of the configuration of a fluid management support system according to an embodiment.

[0024] Figure 2 It is a block diagram illustrating the internal structure of a server device.

[0025] Figure 3 This is a block diagram illustrating the internal structure of the patient terminal.

[0026] Figure 4 This is a block diagram illustrating the internal structure of the doctor's terminal.

[0027] Figure 5 This is a schematic diagram showing an example of a patient information input screen on a patient terminal.

[0028] Figure 6 This is a schematic diagram showing an example of a patient information input screen on a doctor's terminal.

[0029] Figure 7 This is a schematic diagram illustrating an example of the structure of a learning model.

[0030] Figure 8A This is a schematic diagram illustrating an example of image generation.

[0031] Figure 8B This is a schematic diagram illustrating an example of image generation.

[0032] Figure 8C This is a schematic diagram illustrating an example of image generation.

[0033] Figure 9A This is a schematic diagram illustrating a variant example of an image generated in a server device.

[0034] Figure 9B This is a schematic diagram illustrating a variant example of an image generated in a server device.

[0035] Figure 10 This is a flowchart illustrating the processing steps performed by the server device in this embodiment. Detailed Implementation

[0036] The present invention will now be described in detail with reference to the accompanying drawings illustrating embodiments thereof.

[0037] (Implementation Method 1)

[0038] Figure 1 This is a schematic diagram illustrating an example configuration of a fluid management support system according to an embodiment. The fluid management support system of this embodiment includes a server device 10, a patient terminal 20, and a doctor terminal 30. The server device 10 is, for example, a server computer installed in a hospital. The patient terminal 20 is a client computer used by peritoneal dialysis patients (hereinafter also simply referred to as patients), and the doctor terminal 30 is a client computer used by doctors and other medical professionals. The server device 10, patient terminal 20, and doctor terminal 30 are interconnected and can communicate with each other via a communication network NW.

[0039] Server device 10 obtains information about peritoneal dialysis patients (hereinafter referred to as patient information) from patient terminal 20 and doctor terminal 30, and generates an image representing the fluid status of peritoneal dialysis patients based on the obtained patient information.

[0040] The patient information acquired by server device 10 includes information related to at least one of edema, urine output, and fluid loss. This information related to edema, urine output, and fluid loss can be processed through patient terminal 20. The patient information acquired by server device 10 may also include information such as thirst and weight input from patient terminal 20.

[0041] The patient information acquired by server device 10 may further include information related to at least one of hANP, cardiothoracic ratio, bioimpedance, transperitoneal sodium removal, and urinary sodium excretion. This information is patient-managed information, and for example, it may be input from physician terminal 30 and pre-registered in server device 10. The patient information registered in server device 10 may further include information related to antihypertensive agents, diuretics, blood pressure, etc., and may also include information related to urinary cortisol, urinary creatinine, skin sodium levels, Na-MRI, etc.

[0042] Server device 10 outputs images generated based on patient information. For example, server device 10 can also inform the patient of their fluid status by sending the generated images to patient terminal 20 via communication network NW. The patient can then intuitively understand their own fluid status. Optionally, server device 10 can also send the generated images to doctor terminal 30 via communication network NW, informing the healthcare professional of the patient's fluid status. The healthcare professional can then access the patient's fluid status as a community tool to guide appropriate fluid management.

[0043] The following describes the internal structure of the various devices that make up the body fluid management support system.

[0044] Figure 2 This is a block diagram illustrating the internal structure of the server device 10. The server device 10 is a dedicated or general-purpose computer, including a control unit 11, a storage unit 12, a communication unit 13, an operation unit 14, and a display unit 15.

[0045] The control unit 11 includes, for example, a CPU (Central Processing Unit), ROM (Read-Only Memory), and RAM (Random Access Memory). The ROM within the control unit 11 stores control programs that control the operation of various hardware components of the server device 10. The CPU within the control unit 11 reads and executes the control programs stored in the ROM and the computer programs (described later) stored in the storage unit 12 to control the operation of the various hardware components, thereby enabling the entire device to function as the server device 10 (image output device) of this disclosure. The RAM within the control unit 11 temporarily stores data used in the execution of calculations and control.

[0046] In this embodiment, the control unit 11 is configured with a CPU, ROM, and RAM, but the configuration of the control unit 11 is not limited to the above. The control unit 11 may, for example, include one or more control circuits or arithmetic circuits such as a GPU (Graphics Processing Unit), FPGA (Field Programmable Gate Array), DSP (Digital Signal Processor), quantum processor, volatile or non-volatile memory, etc. Furthermore, the control unit 11 may also include functions such as a clock that outputs date and time information, a timer that measures the elapsed time from the issuance of a measurement start command to the issuance of a measurement end command, and a counter that counts quantities.

[0047] Storage unit 12 includes storage devices such as HDD (Hard Disk Drive) and SSD (Solid State Drive). Storage unit 12 stores various computer programs executed by control unit 11 and various data used by control unit 11.

[0048] The computer program (program product) stored in storage unit 12 includes an image generation program PG for causing the computer to perform the following processes: acquiring information about a peritoneal dialysis patient including at least one of edema, urine output, and fluid removal volume; generating an image representing the fluid status of the peritoneal dialysis patient based on the acquired information; and outputting the generated image. The image generation program PG can be a single computer program or a group of programs consisting of multiple computer programs. Furthermore, the image generation program PG may partially utilize existing libraries. The image generation program PG can be executed by a single computer or by multiple computers working together.

[0049] The computer program containing the image generation program PG is provided by a non-temporary recording medium RM on which the computer program is readable. The recording medium RM is a removable memory such as a CD-ROM, USB memory, or SD (Secure Digital) card. The control unit 11 uses a reading device (not shown) to read various computer programs from the recording medium RM and stores the read computer programs in the storage unit 12. The computer program containing the image generation program PG can also be provided via communication. The control unit 11 acquires the computer program containing the image generation program PG through communication via the communication unit 13 and stores the acquired computer program in the storage unit 12.

[0050] Alternatively, a learning model LM can be stored in the storage unit 12. This learning model LM learns to output information related to body fluid status when given input information related to at least one of edema, urine output, and water loss. Regarding the learned learning model LM, the storage unit 12 stores information describing the learning model LM, including its layer structure, the number of nodes constituting each layer, connection relationships, weight coefficients between nodes, and biases, as well as the parameters after learning.

[0051] The communication unit 13 has a communication interface for sending and receiving various data with external devices. The communication interface of the communication unit 13 can use communication interfaces based on communication standards such as WiFi, LAN (Local Area Network), Bluetooth, ZigBee, 3G, 4G, 5G, and LTE (Long Term Evolution). When data to be sent is input from the control unit 11, the communication unit 13 sends the data to the destination external device; when data is received from the external device, the communication unit 13 outputs the received data back to the control unit 11. In this embodiment, an example of an external device is a patient terminal 20 and a doctor terminal 30.

[0052] The operation unit 14 is equipped with operating devices such as a touch panel, keyboard, and switches, and accepts various operations and settings from users. The control unit 11 performs appropriate control based on the various operation information given by the operation unit 14, and stores the setting information in the storage unit 12 as needed.

[0053] The display unit 15 is equipped with display devices such as liquid crystal displays and organic EL (Electro-Luminescence) displays, and displays information to be prompted according to instructions from the control unit 11.

[0054] In this embodiment, the server device 10 can be a single computer or a computer system composed of multiple computers, peripheral devices, etc. Alternatively, the server device 10 can be a virtual machine with physical virtualization or a cloud application.

[0055] Figure 3 This is a block diagram illustrating the internal structure of the patient terminal 20. The patient terminal 20 is a computer such as a smartphone, tablet computer, or personal computer, and includes a control unit 21, a storage unit 22, a communication unit 23, an operation unit 24, and a display unit 25.

[0056] The control unit 21 includes, for example, a CPU, ROM, RAM, etc. The CPU of the control unit 21 executes various programs pre-stored in the ROM or storage unit 22 in the RAM, thereby controlling the operation of the aforementioned hardware and enabling the entire device to function as the patient terminal 20 of this disclosure.

[0057] It should be noted that the control unit 21 is not limited to the above configuration, and may also be configured as a hardware (SoC: System On a Chip) integrating a processor, memory, storage, communication interface, etc. In addition, the control unit 21 may also have functions such as a clock for outputting date and time information, a timer for measuring the elapsed time from the issuance of the measurement start instruction to the issuance of the measurement end instruction, and a counter for counting quantities.

[0058] Storage unit 22 includes memory, hard disk, and other storage devices. Storage unit 22 stores various computer programs executed by control unit 21, as well as data required for the execution of these computer programs. The computer programs stored in storage unit 22 include application programs used to utilize the services provided by server device 10.

[0059] It should be noted that the programs stored in the storage unit 22 can also be provided by a non-temporary recording medium capable of reading and recording the program. Examples of such recording media include removable storage devices such as CD-ROMs, USB drives, and SD cards. The control unit 21 uses a reading device (not shown) to read various programs from the recording medium and installs the read programs into the storage unit 22. Alternatively, the programs stored in the storage unit 22 can also be provided via communication. In this case, the control unit 21 obtains various programs through the communication unit 23 and installs the obtained programs into the storage unit 22.

[0060] The communication unit 23 is equipped with a communication interface for connecting to a communication network NW. The communication interface of the communication unit 23 may be based on communication standards such as WiFi (registered trademark), LAN, Bluetooth (registered trademark), ZigBee (registered trademark), 3G, 4G, 5G, and LTE. The communication unit 23 transmits various information to be notified to the outside and receives various information transmitted to this device from the outside.

[0061] The operation unit 24 is equipped with input devices such as a touch panel and operation buttons, and accepts various operation information and setting information. The operation unit 24 outputs the accepted operation information and setting information to the control unit 21. The control unit 21 performs appropriate control based on the operation information input from the operation unit 24, and stores the setting information in the storage unit 22 as needed.

[0062] The display unit 25 is equipped with display devices such as liquid crystal displays and organic EL displays, and displays information to be prompted to the patient based on control signals output from the control unit 21.

[0063] Figure 4 This is a block diagram illustrating the internal structure of the doctor's terminal 30. The doctor's terminal 30 is a computer such as a personal computer, tablet computer, or smartphone, and includes a control unit 31, a storage unit 32, a communication unit 33, an operation unit 34, and a display unit 35.

[0064] The control unit 31 includes, for example, a CPU, ROM, RAM, etc. The CPU of the control unit 31 executes various programs pre-stored in the ROM or storage unit 32 on the RAM, thereby controlling the operation of the aforementioned hardware and enabling the entire device to function as the doctor terminal 30 of this disclosure.

[0065] It should be noted that the control unit 31 is not limited to the above configuration, and may also be configured as a hardware (SoC: System On a Chip) integrating a processor, memory, storage, communication interface, etc. In addition, the control unit 31 may also have functions such as a clock for outputting date and time information, a timer for measuring the elapsed time from the issuance of the measurement start instruction to the issuance of the measurement end instruction, and a counter for counting quantities.

[0066] The storage unit 32 includes memory, hard disk, and other storage devices. The storage unit 32 stores various computer programs executed by the control unit 31, as well as data required for the execution of these computer programs. The computer programs stored in the storage unit 32 include application programs for using the services provided by the server device 10.

[0067] It should be noted that the programs stored in the storage unit 32 can also be provided by a non-temporary recording medium capable of reading and recording the program. Examples of such recording media include removable storage devices such as CD-ROMs, USB drives, and SD cards. The control unit 31 uses a reading device (not shown) to read various programs from the recording medium and installs the read programs into the storage unit 32. Alternatively, the programs stored in the storage unit 32 can also be provided via communication. In this case, the control unit 31 obtains various programs through the communication unit 33 and installs the obtained programs into the storage unit 32.

[0068] The communication unit 33 has a communication interface for connecting to a communication network NW. The communication interface of the communication unit 33 may be based on communication standards such as WiFi (registered trademark), LAN, Bluetooth (registered trademark), ZigBee (registered trademark), 3G, 4G, 5G, and LTE. The communication unit 33 transmits various information to be notified to the outside and receives various information transmitted to this device from the outside.

[0069] The operation unit 34 is equipped with input devices such as a keyboard and mouse, and accepts various operation information and setting information. The operation unit 34 outputs the accepted operation information and setting information to the control unit 31. The control unit 31 performs appropriate control based on the operation information input from the operation unit 34, and stores the setting information in the storage unit 32 as needed.

[0070] The display unit 35 is equipped with display devices such as liquid crystal displays and organic EL displays, and displays information to be prompted to medical practitioners based on control signals output from the control unit 31.

[0071] The following describes the operation of the fluid management support system.

[0072] When the body fluid management support system of this embodiment displays the patient's own body fluid status on the display unit 25 of the patient terminal 20, the patient can input their own patient information through the operation unit 24 of the patient terminal 20.

[0073] Figure 5 This is a schematic diagram showing an example of a patient information input screen in the patient terminal 20. Figure 5 The patient information input screen shown illustrates an example of a screen displayed on the display unit 25 after a patient terminal 20 accesses the server device 10 and performs a prescribed operation. This patient information input screen receives information related to edema, urine output, and fluid removal.

[0074] The degree of edema is determined by the patient's own assessment of the indentation. Specifically, pressure is applied to the subcutaneous area of ​​the tibia (or other bony structures) using the thumb or the second to fourth fingers. The condition of the skin after the pressure is released is assessed through visual inspection and palpation. Edema of "0" indicates a normal state with no indentation. Edema of "1+" indicates a small indentation without visible deformation that disappears quickly. Edema of "2+" indicates a slightly deeper indentation that disappears in approximately 10-15 seconds. Edema of "3+" indicates an indentation deep enough to last for more than one minute. Edema of "4+" indicates a very deep indentation lasting for more than two to five minutes. Figure 5 The patient information input screen categorizes edema into three states: "0-1+", "2+", and "3+-4+", and the edema status is entered. Optionally, the edema status can also be categorized into five states: "0" to "4+" and entered.

[0075] Urine output is measured by the patient themselves using a measuring cup or similar device. Figure 5 Enter your daily urine output (mL) in the patient information input screen. Fluid removal volume is calculated as infusion volume minus drainage volume. Infusion volume refers to the amount of dialysate injected into the patient's body, determined by measuring the weight of the bag containing the dialysate before and after injection. Drainage volume refers to the amount of dialysate expelled from the patient's body, determined by measuring the weight of the bag storing the expelled fluid. Figure 5 Enter the daily water removal volume (mL) in the patient information input screen.

[0076] exist Figure 5 The image shows a patient information input screen for receiving information related to edema, urine output, and fluid removal, but it can also accept any one or both of these parameters.

[0077] In addition, information on thirst or weight can also be received on the patient information input screen. Thirst is assessed subjectively by the patient using a numerical rating scale (NRS) of 0-10. Optionally, thirst can also be assessed in two phases: with thirst and without thirst. Weight is measured by the patient using a scale.

[0078] In addition, some patient information can also be entered by healthcare professionals. Figure 6 This is a schematic diagram showing an example of a patient information input screen in the doctor's terminal 30. Figure 6 The patient information input screen shown illustrates an example of a screen displayed on the display unit 35 after a doctor's terminal 30 accesses the server device 10 and performs a prescribed operation. This patient information input screen processes information related to hANP, cardiothoracic ratio, bioimpedance, transperitoneal sodium removal, and urinary sodium excretion.

[0079] hANP is the atrial natriuretic peptide, and its concentration is measured through blood tests. The concentration is determined using IRMA (immunoradiometric assay). A baseline hANP value is, for example, 43.0 pg / mL. hAMP is secreted due to atrial stretch stimulation and therefore shows abnormally high levels in diseases and symptoms that cause increased atrial pressure and fluid volume. Figure 6 In the example screen, the concentration of hAMP is entered as a numerical value (pg / mL).

[0080] The cardiothoracic ratio is an indicator of the ratio of the transverse diameter of the heart to the transverse diameter of the thorax, measured using a chest X-ray. An appropriate ratio is below 50% for men and below 55% for women. Increased extracellular fluid volume leads to increased water content in blood vessels, causing the heart to enlarge and thus increasing the cardiothoracic ratio. Figure 6 In the example screen, the heart-chest ratio is entered as a numerical value (%).

[0081] Bioelectrical impedance analysis (BIA) is the electrical resistance (impedance) of an organism, measured using a body composition analyzer. This analyzer utilizes the property that almost no current flows through adipose tissue, but current flows easily through non-adipose tissue containing water and electrolytes. The body composition analyzer can use BIA to measure an indicator of excess / deficient body fluids (OH). The baseline value for OH is -1.1 to 1.1 L. Figure 6 In the example screen, the indicator of excess / insufficient body fluid is entered as a numerical value (L).

[0082] The amount of sodium removed via the peritoneum is determined, for example, by recovering the dialysate (excrement) discharged from the patient during peritoneal dialysis and performing component analysis on the recovered excrement. Figure 6 In the example image, the amount of sodium removed via the peritoneum is entered as a value (g) converted from table salt.

[0083] Urinary sodium removal is measured, for example, by collecting urine from a patient and performing component analysis on the collected urine. Figure 6 In the example screen, the amount of sodium removed in urine is entered as a value (g) converted from table salt.

[0084] exist Figure 6 The example shows a patient information input screen that accepts information related to hANP, cardiothoracic ratio, bioimpedance, transperitoneal sodium removal, and urinary sodium excretion. However, it can also accept any one or more of these information. Furthermore, it is not necessary to accept all information on a single input screen; each piece of information can be accepted individually.

[0085] In addition, information related to at least one of the following can be processed in the patient information input screen: antihypertensive drugs, diuretics, blood pressure, urinary cortisol, urinary creatinine, skin sodium levels, and Na-MRI.

[0086] Patient information input to patient terminal 20 and doctor terminal 30 is sent to server device 10 via communication network NW. Server device 10 generates an image representing the patient's body fluid status based on the patient information obtained from patient terminal 20 and doctor terminal 30. In this embodiment, a learning model LM is used to derive information related to body fluid status from the patient information, and an image representing the patient's body fluid status is generated based on the derived information.

[0087] Figure 7 This is a schematic diagram illustrating an example of the structure of a learning model LM. The learning model LM learns to output information related to the patient's fluid status given input patient information. The learning model LM uses known learning models such as CNN (Convolutional Neural Networks), RNN (Recurrent Neural Networks), LSTM (Long Short Term Memory), and autoencoders.

[0088] The learning model LM comprises an input layer, an intermediate layer, and an output layer. Each layer has one or more nodes. Patient information is input into the nodes of the input layer. Information related to at least one of edema, urine output, and water removal is input into the nodes of the input layer. The information input to the nodes of the input layer may further include at least one of hANP, cardiothoracic ratio, bioimpedance, transperitoneal sodium removal, and urinary sodium excretion. Additionally, the information input to the nodes of the input layer may also include information related to at least one of the patient's weight, thirst, antihypertensive medication, diuretic medication, and blood pressure. Furthermore, the information input to the nodes of the input layer may also include information related to at least one of urinary cortisol, urinary creatinine, skin sodium levels, and Na-MRI.

[0089] The intermediate layers of a learning model (LM) consist of one or more layers. Each node in the intermediate layer connects to nodes in the preceding and following layers. The activation values ​​at each node and the connection strength (weight coefficients) between nodes are determined during the learning process. Each node in a layer outputs a value calculated based on the weight coefficients and activation values ​​to the next node. The output layer calculates probabilities using a flexible maximum activation function based on the values ​​input from the intermediate layers and outputs information based on these probabilities. For example, the output layer calculates the probability of normal fluid volume, the probability of a tendency to excess fluid, and the probability of excess fluid, and outputs information based on these probabilities. For instance, the learning model LM can output information determining whether a patient's fluid volume is normal, has a tendency to excess, or has excess fluid based on the input patient information. Such a learning model LM is generated by using a dataset as training data and learning using existing learning algorithms. This dataset contains patient information such as edema, urine output, and water loss, as well as measured values ​​(positive values) of fluid volume measured using instruments such as body composition analyzers.

[0090] The learned learning model LM is stored in the storage unit 12 of the server device 10. When the control unit 11 of the server device 10 obtains patient information from the patient terminal 20 and the doctor terminal 30, it inputs the obtained patient information into the learning model LM and performs calculations to obtain the calculation results of the learning model LM. In this embodiment, as the calculation results of the learning model LM, information is obtained to determine whether the patient's body fluid volume is normal, has a tendency to be excessive, or is excessive.

[0091] The control unit 11 of the server device 10 generates an image representing the patient's body fluid status based on the computation results of the learning model LM. Figures 8A to 8CThis is a schematic diagram illustrating an example of image generation. Each image shows a first container V1 containing interstitial fluid, a second container V2 containing plasma, a flow path P1 connecting the first and second containers, and an excretion path P2 draining the fluid from the second container. The interstitial fluid contained in the first container V1 and the plasma contained in the second container V2 can flow from one container to the other through the flow path P1. The amount of sodium excreted in the form of urine is shown as the amount of fluid drained through the excretion path P2. Additionally, the amount of sodium removed by dialysis is shown using the number of ">" symbols.

[0092] Figure 8A This demonstrates that sodium removal based on peritoneal dialysis is adequate and fluid management is good. Given that the patient's fluid volume is judged to be normal through the learning model LM, the control unit 11 generates... Figure 8A The image shown is displayed and output. The output destination can be either the patient terminal 20 or the doctor terminal 30.

[0093] Figure 8B This indicates inadequate sodium removal and slightly poor fluid management based on peritoneal dialysis. When the learning model LM indicates a tendency for excess fluid in the patient, control unit 11... Figure 8B As shown, an image with slightly higher interstitial fluid and plasma volumes is generated and output to the patient terminal 20 or the doctor terminal 30.

[0094] Figure 8C This demonstrates unsuccessful sodium removal and poor fluid management based on peritoneal dialysis. When the patient's fluid excess is determined by the learning model LM, the control unit 11... Figure 8C As shown, images of the first container V1 and the second container V2 being filled with interstitial fluid and plasma, respectively, are generated and output to the patient terminal 20 or the doctor terminal 30.

[0095] exist Figures 8A to 8C In the example, in addition to the patient's body fluid volume (interstitial fluid volume and plasma volume), images are shown showing the amount of sodium excreted in urine and the amount of sodium removed by dialysis. However, the sodium volume can be omitted to generate an image showing only the body fluid volume.

[0096] Patient terminal 20 receives from server device 10 Figures 8A to 8C In the case of the image shown, the display unit 25 displays the received image. By reviewing the image displayed on the display unit 25, the patient can intuitively understand their own bodily fluid status.

[0097] The doctor terminal 30 receives from the server device 10 Figures 8A to 8CIn the case of the image shown, the display unit 35 displays the received image. By reviewing the image displayed on the display unit 35, medical practitioners can understand the patient's fluid status, which can be used as a community tool to guide appropriate fluid management.

[0098] Figure 9A and Figure 9B This is a schematic diagram illustrating a modified example of an image generated in server device 10. Figure 9A and Figure 9B The diagram illustrates the balance between sodium intake and sodium excretion. As can be seen from the diagram, even when sodium intake and sodium excreted in urine through residual kidney function (residual kidney) are roughly constant, the sodium balance is disrupted when sodium removal varies due to peritoneal dialysis (PD).

[0099] Figure 10 This is a flowchart illustrating the processing steps performed by the server device 10 in this embodiment. The server device 10 obtains patient information from the patient terminal 20 and the doctor terminal 30 via the communication network NW (step S101). The patient information obtained by the server device 10 includes information related to at least one of edema, urine output, and water removal. In addition to this information, information such as hANP, cardiothoracic ratio, bioimpedance, transperitoneal sodium removal, and urinary sodium excretion can also be obtained.

[0100] The control unit 11 of the server device 10 inputs the acquired patient information into the learning model LM and performs calculations based on the learning model LM (step S102). As the result of the calculations of the learning model LM, the control unit 11 acquires information related to the patient's body fluid status (step S103).

[0101] Based on information related to the acquired patient's body fluid status, control unit 11 generates an image representing the patient's body fluid status (step S104). Control unit 11 generates images that differentiate the amount of interstitial fluid in the first container V1 from the amount of plasma in the second container V2, depending on whether the body fluid volume is normal, has a tendency to be excessive, or is excessive. Figures 8A-8C The image shown is sufficient. Additionally, as... Figures 8A-8C As shown, the control unit 11 can also generate images that vary the amount of sodium removed by dialysis based on the amount of interstitial fluid and plasma. Optionally, the control unit 11 can also generate images that schematically show the balance between the amount of sodium ingested and the amount of sodium excreted. Figures 9A to 9B The image shown.

[0102] The control unit 11 sends the generated image to the patient terminal 20 or the doctor terminal 30 (step S105). The image sent from the server device 10 arrives at the patient terminal 20 or the doctor terminal 30 via the communication network NW. Upon receiving the image sent from the server device 10, the patient terminal 20 causes the display unit 25 to display the received image. Upon receiving the image sent from the server device 10, the doctor terminal 30 causes the display unit 35 to display the received image.

[0103] As described above, in this embodiment, the patient's fluid status can be displayed to the patient or to a healthcare professional. The patient can intuitively understand their own fluid status by reviewing the images displayed on the display unit 25 of the patient terminal 20. Healthcare professionals can monitor the patient's fluid status by reviewing the images displayed on the display unit 35 of the doctor's terminal 30, and use this information as a community tool to guide appropriate fluid management.

[0104] It should be understood that the embodiments disclosed herein are illustrative in all respects and not limiting. The scope of the invention is defined not in the foregoing sense but by the claims, and is intended to include all modifications within the meaning and scope equivalent to the claims.

[0105] For example, in this embodiment, the server device 10 is configured to perform calculations based on the learning model LM and use the calculation results of the learning model LM to generate an image. However, the calculations of the learning model LM can also be performed separately in the patient terminal 20 and the doctor terminal 30, and the calculation results of the learning model LM can be used to generate an image. In this case, the image generation program PG and the learning model LM are installed in each of the patient terminal 20 and the doctor terminal 30.

[0106] In this embodiment, patient information is input into a learning model LM to obtain information related to body fluid status, and an image representing the patient's body fluid status is generated based on the obtained information. However, it can also be configured to use a learning model of an image generation system such as GAN (Generative Adversarial Network) or PGGAN (Progressive Growing of GANs) to directly generate an image representing the patient's body fluid status from the patient information. Explanation of reference numerals in the attached figures

[0107] 10 server devices

[0108] 11 Control Department

[0109] 12 Storage Units

[0110] 13Ministry of Communications

[0111] 14 Operations Department

[0112] 15 Display Section

[0113] 20 patient terminals

[0114] 21 Control Department

[0115] 22 Storage Department

[0116] 23 Ministry of Communications

[0117] 24 Operations Department

[0118] 25 Display Section

[0119] 30 Doctor Terminal

[0120] 31 Control Department

[0121] 32 Storage Unit

[0122] 33 Ministry of Communications

[0123] 34 Operations Department

[0124] 35 Display Unit

[0125] PG image generation program

[0126] LM learning model.

Claims

1. A computer program, characterized in that, Used to enable the computer to perform the following processes: Obtain information on peritoneal dialysis patients that includes at least one of the following: edema, urine output, and fluid removal volume; Based on the acquired information, an image representing the fluid status of the peritoneal dialysis patient is generated; Output the generated image.

2. The computer program according to claim 1, characterized in that, The information also includes information relating to at least one of hANP, cardiothoracic ratio, bioimpedance, transperitoneal sodium removal, and urinary sodium excretion, wherein hANP is atrial natriuretic peptide.

3. The computer program according to claim 2, characterized in that, The information also includes information relating to at least one of the peritoneal dialysis patient’s weight, thirst, antihypertensive medication, diuretic medication, and blood pressure.

4. The computer program according to claim 3, characterized in that, The information also includes information relating to at least one of urinary cortisol, urinary creatinine, skin sodium levels, and Na-MRI, where Na-MRI is sodium magnetic resonance imaging.

5. The computer program according to claim 1, characterized in that, To enable the computer to perform the following processes: As the image, an image is generated that schematically represents the sodium reserves and sodium excretion of the peritoneal dialysis patient.

6. The computer program according to claim 5, characterized in that, To enable the computer to perform the following processes: As the image, an image is generated containing a first container holding interstitial fluid and a second container holding plasma, and the amount of sodium stored is represented according to the amount of interstitial fluid in the first container.

7. The computer program according to claim 6, characterized in that, To enable the computer to perform the following processes: As the image, an image is generated showing the flow path of the interstitial fluid and plasma between the first and second containers, and the excretion path of sodium being excreted from the second container in the form of urine. The image schematically represents the sodium excretion based on the amount of sodium removed from the plasma via peritoneal dialysis and the amount of sodium excreted through the excretory pathway.

8. The computer program according to claim 1, characterized in that, To enable the computer to perform the following processes: As the image, an image is generated that schematically represents the balance between sodium intake and sodium excretion in the peritoneal dialysis patient.

9. The computer program according to any one of claims 1 to 8, characterized in that, To enable the computer to perform the following processes: The acquired information of the peritoneal dialysis patients is input into a learning model, and calculations based on the learning model are performed. The learning model learns to output information related to fluid status in response to input information related to at least one of edema, urine output, and fluid removal. Based on the computational results of the learning model, an image representing the fluid status of the peritoneal dialysis patient is generated.

10. An image output method, characterized in that, The computer performs the following processing: Obtain information on peritoneal dialysis patients that includes at least one of the following: edema, urine output, and fluid removal volume; Based on the acquired information, an image representing the fluid status of the peritoneal dialysis patient is generated; Output the generated image.

11. An image output device, characterized in that, It has at least one processor. The processor acquires information about peritoneal dialysis patients, including at least one of edema, urine output, and fluid removal volume. Based on the acquired information, an image representing the fluid status of the peritoneal dialysis patient is generated. Output the generated image.

Images